Дмитрий
09598dd5bd
Производство двух печатей (артефакт-решение + план-шаги), чтобы стене М2 было
что матчить — код-предусловие флипа. Inline TDD, спека/план одобрены владельцем.
- C1 artifact-from-spec.mjs: спека markdown -> {sections, source_sha} по якорям {#id} (P2-2).
- C2 plan-steps-parse.mjs: план -> [{op,object,ref}], fail-CLOSE, reject op:Task (VA-4),
канон object = repo-relative POSIX (SE-5; pathNormalize только на матче в стене, не на парсе).
- C3/C4 plan-lock.mjs: judge_mode в ПОДПИСАННОЙ базе freezePlan (VA-2) + атомарный persist
temp->rename для обоих save (SE-4/VA-3, артефакт ДО плана).
- C6 seal-orchestration.mjs: sealableArtifact/sealablePlan + judgedHashOf (SD-1) +
sealArtifact/sealPlan на РЕАЛЬНОМ GO (SE-3 wired===true), штамп artifact_id из текущего
артефакта (SD-3), judge_mode впрыснут в печать ПОСЛЕ хеш-сверки sealOnApproval (фикс TOCTOU).
- C5 enforce-judge-gate.mjs: SPEC_PATH_RE + sealOnWiredGo (печать на wired GO, инъекция в main,
юнит-тесты hermetic) + judged_hash в вердикте runJudgeGate. extractGate2Product не тронут
(Гейт-2 = планы; Гейт-1 spec-judging — отдельный заход перед флипом).
- Интеграция seal-to-wall: печать -> decideMode стены М2 (allow / non-match block / closed-door).
Тесты: full tools-only регрессия 3427 passed | 2 skipped, 0 регрессий (+29 новых кейсов).
Печать в рантайме НЕ производится до флипа (стена/судья не зарегистрированы) — сборка
готовит код-предусловие. Спека docs/superpowers/specs/2026-06-09-sealed-plan-production-design.md.
Observer infrastructure
Passive evidence-loop for the Лидерра «brain» per ADR-011.
Files
episodes-YYYY-MM.jsonl— append-only JSONL, one line per Stop-event. Schema v2 (schema_version: 2): the 5 mandatory fields +decision_provenance(who chose the node),environment(economy_level / model / post_compaction / session_turn / parallel_session),task_size,task_ref,prompt_signal, and anoutcomethat isunknownat write time (refined by/brain-retro). On an internal hook failure a minimalobserver_errormarker line is written instead of a silent skip. Written bytools/observer-stop-hook.mjsviatools/observer-transcript-parser.mjs.notes/YYYY-MM-DD-<slug>.md— optional MD notes for sessions with qualitative history.STATUS.md— auto-generated dashboard. Regenerated per-commit bytools/status-md-generator.mjs..read-counter.json— C3 observer-of-observer counter. Updated on Read of observer files.dashboard.html+dashboard.js+dashboard-core.js— Brain Dashboard: visualises the episode log over the automation-graph topology (4 views — Карта / Разбор / Лента / Агрегат). Runnpm run brain:dashboard, open the printed localhost URL.dashboard-core.jsis pure logic, unit-tested intools/brain-dashboard-core.test.mjs.
Lifecycle
- Write: every Stop-event appends one JSONL line, parsed from the session transcript (Stop-hook).
- Aggregate:
/brain-retroskill reads JSONL each sprint, proposes regulatory candidates. - Surface:
STATUS.mdshows controllers + monthly stats. - Self-prune: C3 warns if 54 weeks pass without any read of observer files.
Routing-tag discipline
When the user dictates a specific method/node (e.g. «запусти discovery-interview»), Claude must emit one line in its response:
<!-- routing: provenance=user_directed_method node=<chosen> counterfactual=<node Claude would have chosen autonomously> -->
The Stop-hook routing-gate (tools/observer-routing-detector.mjs + routingGateDecision) detects a dictated method; if the tag is missing it returns decision: block, so the turn cannot end without the tag. The gate fires at most once per turn (stop_hook_active guard). This makes decision_provenance reliable — factor analysis can separate a router error from a user-dictated one.
Privacy
PII filter (phone numbers, emails, tokens) is applied before every write — see tools/observer-pii-filter.mjs. gitleaks pre-push also scans observer files as part of full-history sweep.
Don't
- Don't edit
episodes-*.jsonlmanually — it's append-only. - Don't write outside
docs/observer/notes/for hand-curated notes. - Don't change
.read-counter.jsonmanually — it's maintained by hooks.
HK1 pre-check (Pravila ADR-010) — verified 2026-05-19
Before registering tools/observer-stop-hook.mjs on Stop event (Task B5), verified collision against 6-component economy/skill-discipline architecture:
- User-level
~/.claude/settings.jsonalready has Stop hook: agent-type Sonnet-4.6 economy compliance verifier (analyzes transcript for claim-without-evidence violations). - Project-level
.claude/settings.json— Stop slot empty.
Result: no overwrite. observer-stop-hook will be added as command-type entry in project-level Stop array. Project + user scopes are independent slots in Claude Code 2.x — both run on the same Stop event without conflict. The agent verifier (user scope) and the JSONL appender (project scope) have non-overlapping responsibilities.